Authors: Changhee Han, Kyohei Shibano, Wataru Ozaki, Keishiro Osaki, Takafumi Haraguchi, Daisuke Hirahara, Shumon Kimura, Yasuyuki Kobayashi, Gento Mogi

Published on: March 10, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2403.06145

Summary

• What is new: The establishment of the first commercial medical imaging platform focusing on under-represented data from Asia, and plans to use Blockchain and generative AI for data security and synthesizing rare disease data.
• Why this is important: Significant data imbalance in medical imaging RD, with a lack of data from Asia, and the high time and financial costs required to curate proprietary datasets for commercial use.
• What the research proposes: A commercial platform for collecting, selecting, annotating, and preprocessing medical imaging data, specifically targeting underrepresented regions such as Japan and broader Asia.
• Results: Preparation and provision of ready-to-use datasets for medical AI RD to AI firms, biopharma, and medical device makers, enabling the development of tailored AI solutions.

Technical Details

Technological frameworks used: Blockchain for data security, generative AI for synthesizing data.

Models used: AI models for medical imaging.

Data used: Computed Tomography, Magnetic Resonance Imaging, and Whole Slide Imaging scans from Asia.

Potential Impact

Medical imaging, AI firms, biopharma, and medical device makers potentially benefit from more diverse and secure datasets.

Want to implement this idea in a business?

We have generated a startup concept here: MediHubAI.